{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:41Z","timestamp":1740165821341,"version":"3.37.3"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"MSIT (No","award":["0000DONOTUSETHIS0000.RS-2023-00252391"],"award-info":[{"award-number":["0000DONOTUSETHIS0000.RS-2023-00252391"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3323560","type":"journal-article","created":{"date-parts":[[2023,10,19]],"date-time":"2023-10-19T18:14:20Z","timestamp":1697739260000},"page":"341-353","source":"Crossref","is-referenced-by-count":1,"title":["Enabling Visual Object Detection With Object Sounds via Visual Modality Recalling Memory"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4533-4875","authenticated-orcid":false,"given":"Jung Uk","family":"Kim","sequence":"first","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref2","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Ren"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933451"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01144"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965417"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00995"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1327250"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3161314"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s13164-009-0004-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)00138-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0812"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01027"},{"key":"ref18","first-page":"14961","article-title":"See, hear, explore: Curiosity via audio-visual association","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Dean"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/35012613"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16447"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0920-9964(01)00344-9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076466"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3105143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00596"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00034"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900709"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01266"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00255"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00739"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00304"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01273"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref40","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Hu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00097"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102605"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00877"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00717"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00440"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00449"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20001"},{"key":"ref59","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Glorot"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3001940"},{"key":"ref62","first-page":"1","article-title":"Pay attention to features, transfer learn faster CNNs","volume-title":"Proc. Int. Conf. Learning. Represent. (ICLR)","author":"Wang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref65","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01174"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-792"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1768"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10287964.pdf?arnumber=10287964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:24:19Z","timestamp":1736367859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10287964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":69,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3323560","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}